auphong2707 commited on
Commit
f628870
·
verified ·
1 Parent(s): 8e7e912

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Salesforce/codet5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 3072,
9
+ "d_kv": 64,
10
+ "d_model": 768,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "relu",
13
+ "dropout_rate": 0.1,
14
+ "eos_token_id": 2,
15
+ "feed_forward_proj": "relu",
16
+ "gradient_checkpointing": false,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_factor": 1.0,
21
+ "is_encoder_decoder": true,
22
+ "is_gated_act": false,
23
+ "label2id": {
24
+ "LABEL_0": 0
25
+ },
26
+ "layer_norm_epsilon": 1e-06,
27
+ "model_type": "t5",
28
+ "n_positions": 512,
29
+ "num_decoder_layers": 12,
30
+ "num_heads": 12,
31
+ "num_layers": 12,
32
+ "output_past": true,
33
+ "pad_token_id": 0,
34
+ "relative_attention_max_distance": 128,
35
+ "relative_attention_num_buckets": 32,
36
+ "task_specific_params": {
37
+ "summarization": {
38
+ "early_stopping": true,
39
+ "length_penalty": 2.0,
40
+ "max_length": 200,
41
+ "min_length": 30,
42
+ "no_repeat_ngram_size": 3,
43
+ "num_beams": 4,
44
+ "prefix": "summarize: "
45
+ },
46
+ "translation_en_to_de": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to German: "
51
+ },
52
+ "translation_en_to_fr": {
53
+ "early_stopping": true,
54
+ "max_length": 300,
55
+ "num_beams": 4,
56
+ "prefix": "translate English to French: "
57
+ },
58
+ "translation_en_to_ro": {
59
+ "early_stopping": true,
60
+ "max_length": 300,
61
+ "num_beams": 4,
62
+ "prefix": "translate English to Romanian: "
63
+ }
64
+ },
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.46.0",
67
+ "use_cache": true,
68
+ "vocab_size": 32100
69
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "decoder_start_token_id": 0,
5
+ "eos_token_id": 2,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.46.0"
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d0725d52d788523faf9eb0a7e3d75fbdeb602a824a062d697ab96f88c7f1b49
3
+ size 891558696
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae7e3e740e0172ea4d66c75dea0059b13bd674e532a6f8f81849a35a73831596
3
+ size 1783273227
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecbaa8ece86314f0437f294edd4be4e6ac221552abf5f694c4deff9f4d934f9e
3
+ size 14917
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb798fed02a428300b5bfacf5b5a0d127bc9275fec3db49d1ed74d4d9f0e4ab3
3
+ size 14917
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9534931dd473ed5d6b2110458a3419d3c291c6ec91df74a5e392016533935c58
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,753 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<extra_id_99>",
5
+ "lstrip": true,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<extra_id_98>",
12
+ "lstrip": true,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<extra_id_97>",
19
+ "lstrip": true,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<extra_id_96>",
26
+ "lstrip": true,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<extra_id_95>",
33
+ "lstrip": true,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<extra_id_94>",
40
+ "lstrip": true,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<extra_id_93>",
47
+ "lstrip": true,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<extra_id_92>",
54
+ "lstrip": true,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<extra_id_91>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "<extra_id_90>",
68
+ "lstrip": true,
69
+ "normalized": true,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<extra_id_89>",
75
+ "lstrip": true,
76
+ "normalized": true,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "<extra_id_88>",
82
+ "lstrip": true,
83
+ "normalized": true,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<extra_id_87>",
89
+ "lstrip": true,
90
+ "normalized": true,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "<extra_id_86>",
96
+ "lstrip": true,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "<extra_id_85>",
103
+ "lstrip": true,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "<extra_id_84>",
110
+ "lstrip": true,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "<extra_id_83>",
117
+ "lstrip": true,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "<extra_id_82>",
124
+ "lstrip": true,
125
+ "normalized": true,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "<extra_id_81>",
131
+ "lstrip": true,
132
+ "normalized": true,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "<extra_id_80>",
138
+ "lstrip": true,
139
+ "normalized": true,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "<extra_id_79>",
145
+ "lstrip": true,
146
+ "normalized": true,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "<extra_id_78>",
152
+ "lstrip": true,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ },
157
+ {
158
+ "content": "<extra_id_77>",
159
+ "lstrip": true,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false
163
+ },
164
+ {
165
+ "content": "<extra_id_76>",
166
+ "lstrip": true,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false
170
+ },
171
+ {
172
+ "content": "<extra_id_75>",
173
+ "lstrip": true,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false
177
+ },
178
+ {
179
+ "content": "<extra_id_74>",
180
+ "lstrip": true,
181
+ "normalized": true,
182
+ "rstrip": false,
183
+ "single_word": false
184
+ },
185
+ {
186
+ "content": "<extra_id_73>",
187
+ "lstrip": true,
188
+ "normalized": true,
189
+ "rstrip": false,
190
+ "single_word": false
191
+ },
192
+ {
193
+ "content": "<extra_id_72>",
194
+ "lstrip": true,
195
+ "normalized": true,
196
+ "rstrip": false,
197
+ "single_word": false
198
+ },
199
+ {
200
+ "content": "<extra_id_71>",
201
+ "lstrip": true,
202
+ "normalized": true,
203
+ "rstrip": false,
204
+ "single_word": false
205
+ },
206
+ {
207
+ "content": "<extra_id_70>",
208
+ "lstrip": true,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ {
214
+ "content": "<extra_id_69>",
215
+ "lstrip": true,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ {
221
+ "content": "<extra_id_68>",
222
+ "lstrip": true,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ {
228
+ "content": "<extra_id_67>",
229
+ "lstrip": true,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ {
235
+ "content": "<extra_id_66>",
236
+ "lstrip": true,
237
+ "normalized": true,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ {
242
+ "content": "<extra_id_65>",
243
+ "lstrip": true,
244
+ "normalized": true,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ {
249
+ "content": "<extra_id_64>",
250
+ "lstrip": true,
251
+ "normalized": true,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ },
255
+ {
256
+ "content": "<extra_id_63>",
257
+ "lstrip": true,
258
+ "normalized": true,
259
+ "rstrip": false,
260
+ "single_word": false
261
+ },
262
+ {
263
+ "content": "<extra_id_62>",
264
+ "lstrip": true,
265
+ "normalized": true,
266
+ "rstrip": false,
267
+ "single_word": false
268
+ },
269
+ {
270
+ "content": "<extra_id_61>",
271
+ "lstrip": true,
272
+ "normalized": true,
273
+ "rstrip": false,
274
+ "single_word": false
275
+ },
276
+ {
277
+ "content": "<extra_id_60>",
278
+ "lstrip": true,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false
282
+ },
283
+ {
284
+ "content": "<extra_id_59>",
285
+ "lstrip": true,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false
289
+ },
290
+ {
291
+ "content": "<extra_id_58>",
292
+ "lstrip": true,
293
+ "normalized": true,
294
+ "rstrip": false,
295
+ "single_word": false
296
+ },
297
+ {
298
+ "content": "<extra_id_57>",
299
+ "lstrip": true,
300
+ "normalized": true,
301
+ "rstrip": false,
302
+ "single_word": false
303
+ },
304
+ {
305
+ "content": "<extra_id_56>",
306
+ "lstrip": true,
307
+ "normalized": true,
308
+ "rstrip": false,
309
+ "single_word": false
310
+ },
311
+ {
312
+ "content": "<extra_id_55>",
313
+ "lstrip": true,
314
+ "normalized": true,
315
+ "rstrip": false,
316
+ "single_word": false
317
+ },
318
+ {
319
+ "content": "<extra_id_54>",
320
+ "lstrip": true,
321
+ "normalized": true,
322
+ "rstrip": false,
323
+ "single_word": false
324
+ },
325
+ {
326
+ "content": "<extra_id_53>",
327
+ "lstrip": true,
328
+ "normalized": true,
329
+ "rstrip": false,
330
+ "single_word": false
331
+ },
332
+ {
333
+ "content": "<extra_id_52>",
334
+ "lstrip": true,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false
338
+ },
339
+ {
340
+ "content": "<extra_id_51>",
341
+ "lstrip": true,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false
345
+ },
346
+ {
347
+ "content": "<extra_id_50>",
348
+ "lstrip": true,
349
+ "normalized": true,
350
+ "rstrip": false,
351
+ "single_word": false
352
+ },
353
+ {
354
+ "content": "<extra_id_49>",
355
+ "lstrip": true,
356
+ "normalized": true,
357
+ "rstrip": false,
358
+ "single_word": false
359
+ },
360
+ {
361
+ "content": "<extra_id_48>",
362
+ "lstrip": true,
363
+ "normalized": true,
364
+ "rstrip": false,
365
+ "single_word": false
366
+ },
367
+ {
368
+ "content": "<extra_id_47>",
369
+ "lstrip": true,
370
+ "normalized": true,
371
+ "rstrip": false,
372
+ "single_word": false
373
+ },
374
+ {
375
+ "content": "<extra_id_46>",
376
+ "lstrip": true,
377
+ "normalized": true,
378
+ "rstrip": false,
379
+ "single_word": false
380
+ },
381
+ {
382
+ "content": "<extra_id_45>",
383
+ "lstrip": true,
384
+ "normalized": true,
385
+ "rstrip": false,
386
+ "single_word": false
387
+ },
388
+ {
389
+ "content": "<extra_id_44>",
390
+ "lstrip": true,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false
394
+ },
395
+ {
396
+ "content": "<extra_id_43>",
397
+ "lstrip": true,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false
401
+ },
402
+ {
403
+ "content": "<extra_id_42>",
404
+ "lstrip": true,
405
+ "normalized": true,
406
+ "rstrip": false,
407
+ "single_word": false
408
+ },
409
+ {
410
+ "content": "<extra_id_41>",
411
+ "lstrip": true,
412
+ "normalized": true,
413
+ "rstrip": false,
414
+ "single_word": false
415
+ },
416
+ {
417
+ "content": "<extra_id_40>",
418
+ "lstrip": true,
419
+ "normalized": true,
420
+ "rstrip": false,
421
+ "single_word": false
422
+ },
423
+ {
424
+ "content": "<extra_id_39>",
425
+ "lstrip": true,
426
+ "normalized": true,
427
+ "rstrip": false,
428
+ "single_word": false
429
+ },
430
+ {
431
+ "content": "<extra_id_38>",
432
+ "lstrip": true,
433
+ "normalized": true,
434
+ "rstrip": false,
435
+ "single_word": false
436
+ },
437
+ {
438
+ "content": "<extra_id_37>",
439
+ "lstrip": true,
440
+ "normalized": true,
441
+ "rstrip": false,
442
+ "single_word": false
443
+ },
444
+ {
445
+ "content": "<extra_id_36>",
446
+ "lstrip": true,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false
450
+ },
451
+ {
452
+ "content": "<extra_id_35>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false
457
+ },
458
+ {
459
+ "content": "<extra_id_34>",
460
+ "lstrip": true,
461
+ "normalized": true,
462
+ "rstrip": false,
463
+ "single_word": false
464
+ },
465
+ {
466
+ "content": "<extra_id_33>",
467
+ "lstrip": true,
468
+ "normalized": true,
469
+ "rstrip": false,
470
+ "single_word": false
471
+ },
472
+ {
473
+ "content": "<extra_id_32>",
474
+ "lstrip": true,
475
+ "normalized": true,
476
+ "rstrip": false,
477
+ "single_word": false
478
+ },
479
+ {
480
+ "content": "<extra_id_31>",
481
+ "lstrip": true,
482
+ "normalized": true,
483
+ "rstrip": false,
484
+ "single_word": false
485
+ },
486
+ {
487
+ "content": "<extra_id_30>",
488
+ "lstrip": true,
489
+ "normalized": true,
490
+ "rstrip": false,
491
+ "single_word": false
492
+ },
493
+ {
494
+ "content": "<extra_id_29>",
495
+ "lstrip": true,
496
+ "normalized": true,
497
+ "rstrip": false,
498
+ "single_word": false
499
+ },
500
+ {
501
+ "content": "<extra_id_28>",
502
+ "lstrip": true,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false
506
+ },
507
+ {
508
+ "content": "<extra_id_27>",
509
+ "lstrip": true,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false
513
+ },
514
+ {
515
+ "content": "<extra_id_26>",
516
+ "lstrip": true,
517
+ "normalized": true,
518
+ "rstrip": false,
519
+ "single_word": false
520
+ },
521
+ {
522
+ "content": "<extra_id_25>",
523
+ "lstrip": true,
524
+ "normalized": true,
525
+ "rstrip": false,
526
+ "single_word": false
527
+ },
528
+ {
529
+ "content": "<extra_id_24>",
530
+ "lstrip": true,
531
+ "normalized": true,
532
+ "rstrip": false,
533
+ "single_word": false
534
+ },
535
+ {
536
+ "content": "<extra_id_23>",
537
+ "lstrip": true,
538
+ "normalized": true,
539
+ "rstrip": false,
540
+ "single_word": false
541
+ },
542
+ {
543
+ "content": "<extra_id_22>",
544
+ "lstrip": true,
545
+ "normalized": true,
546
+ "rstrip": false,
547
+ "single_word": false
548
+ },
549
+ {
550
+ "content": "<extra_id_21>",
551
+ "lstrip": true,
552
+ "normalized": true,
553
+ "rstrip": false,
554
+ "single_word": false
555
+ },
556
+ {
557
+ "content": "<extra_id_20>",
558
+ "lstrip": true,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false
562
+ },
563
+ {
564
+ "content": "<extra_id_19>",
565
+ "lstrip": true,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false
569
+ },
570
+ {
571
+ "content": "<extra_id_18>",
572
+ "lstrip": true,
573
+ "normalized": true,
574
+ "rstrip": false,
575
+ "single_word": false
576
+ },
577
+ {
578
+ "content": "<extra_id_17>",
579
+ "lstrip": true,
580
+ "normalized": true,
581
+ "rstrip": false,
582
+ "single_word": false
583
+ },
584
+ {
585
+ "content": "<extra_id_16>",
586
+ "lstrip": true,
587
+ "normalized": true,
588
+ "rstrip": false,
589
+ "single_word": false
590
+ },
591
+ {
592
+ "content": "<extra_id_15>",
593
+ "lstrip": true,
594
+ "normalized": true,
595
+ "rstrip": false,
596
+ "single_word": false
597
+ },
598
+ {
599
+ "content": "<extra_id_14>",
600
+ "lstrip": true,
601
+ "normalized": true,
602
+ "rstrip": false,
603
+ "single_word": false
604
+ },
605
+ {
606
+ "content": "<extra_id_13>",
607
+ "lstrip": true,
608
+ "normalized": true,
609
+ "rstrip": false,
610
+ "single_word": false
611
+ },
612
+ {
613
+ "content": "<extra_id_12>",
614
+ "lstrip": true,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false
618
+ },
619
+ {
620
+ "content": "<extra_id_11>",
621
+ "lstrip": true,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false
625
+ },
626
+ {
627
+ "content": "<extra_id_10>",
628
+ "lstrip": true,
629
+ "normalized": true,
630
+ "rstrip": false,
631
+ "single_word": false
632
+ },
633
+ {
634
+ "content": "<extra_id_9>",
635
+ "lstrip": true,
636
+ "normalized": true,
637
+ "rstrip": false,
638
+ "single_word": false
639
+ },
640
+ {
641
+ "content": "<extra_id_8>",
642
+ "lstrip": true,
643
+ "normalized": true,
644
+ "rstrip": false,
645
+ "single_word": false
646
+ },
647
+ {
648
+ "content": "<extra_id_7>",
649
+ "lstrip": true,
650
+ "normalized": true,
651
+ "rstrip": false,
652
+ "single_word": false
653
+ },
654
+ {
655
+ "content": "<extra_id_6>",
656
+ "lstrip": true,
657
+ "normalized": true,
658
+ "rstrip": false,
659
+ "single_word": false
660
+ },
661
+ {
662
+ "content": "<extra_id_5>",
663
+ "lstrip": true,
664
+ "normalized": true,
665
+ "rstrip": false,
666
+ "single_word": false
667
+ },
668
+ {
669
+ "content": "<extra_id_4>",
670
+ "lstrip": true,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false
674
+ },
675
+ {
676
+ "content": "<extra_id_3>",
677
+ "lstrip": true,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false
681
+ },
682
+ {
683
+ "content": "<extra_id_2>",
684
+ "lstrip": true,
685
+ "normalized": true,
686
+ "rstrip": false,
687
+ "single_word": false
688
+ },
689
+ {
690
+ "content": "<extra_id_1>",
691
+ "lstrip": true,
692
+ "normalized": true,
693
+ "rstrip": false,
694
+ "single_word": false
695
+ },
696
+ {
697
+ "content": "<extra_id_0>",
698
+ "lstrip": true,
699
+ "normalized": true,
700
+ "rstrip": false,
701
+ "single_word": false
702
+ }
703
+ ],
704
+ "bos_token": {
705
+ "content": "<s>",
706
+ "lstrip": false,
707
+ "normalized": true,
708
+ "rstrip": false,
709
+ "single_word": false
710
+ },
711
+ "cls_token": {
712
+ "content": "<s>",
713
+ "lstrip": false,
714
+ "normalized": true,
715
+ "rstrip": false,
716
+ "single_word": false
717
+ },
718
+ "eos_token": {
719
+ "content": "</s>",
720
+ "lstrip": false,
721
+ "normalized": true,
722
+ "rstrip": false,
723
+ "single_word": false
724
+ },
725
+ "mask_token": {
726
+ "content": "<mask>",
727
+ "lstrip": true,
728
+ "normalized": true,
729
+ "rstrip": false,
730
+ "single_word": false
731
+ },
732
+ "pad_token": {
733
+ "content": "<pad>",
734
+ "lstrip": false,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false
738
+ },
739
+ "sep_token": {
740
+ "content": "</s>",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false
745
+ },
746
+ "unk_token": {
747
+ "content": "<unk>",
748
+ "lstrip": false,
749
+ "normalized": true,
750
+ "rstrip": false,
751
+ "single_word": false
752
+ }
753
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,959 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32000": {
45
+ "content": "<extra_id_99>",
46
+ "lstrip": true,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32001": {
53
+ "content": "<extra_id_98>",
54
+ "lstrip": true,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32002": {
61
+ "content": "<extra_id_97>",
62
+ "lstrip": true,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32003": {
69
+ "content": "<extra_id_96>",
70
+ "lstrip": true,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32004": {
77
+ "content": "<extra_id_95>",
78
+ "lstrip": true,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32005": {
85
+ "content": "<extra_id_94>",
86
+ "lstrip": true,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32006": {
93
+ "content": "<extra_id_93>",
94
+ "lstrip": true,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32007": {
101
+ "content": "<extra_id_92>",
102
+ "lstrip": true,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32008": {
109
+ "content": "<extra_id_91>",
110
+ "lstrip": true,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32009": {
117
+ "content": "<extra_id_90>",
118
+ "lstrip": true,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32010": {
125
+ "content": "<extra_id_89>",
126
+ "lstrip": true,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32011": {
133
+ "content": "<extra_id_88>",
134
+ "lstrip": true,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32012": {
141
+ "content": "<extra_id_87>",
142
+ "lstrip": true,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32013": {
149
+ "content": "<extra_id_86>",
150
+ "lstrip": true,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32014": {
157
+ "content": "<extra_id_85>",
158
+ "lstrip": true,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32015": {
165
+ "content": "<extra_id_84>",
166
+ "lstrip": true,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32016": {
173
+ "content": "<extra_id_83>",
174
+ "lstrip": true,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32017": {
181
+ "content": "<extra_id_82>",
182
+ "lstrip": true,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32018": {
189
+ "content": "<extra_id_81>",
190
+ "lstrip": true,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32019": {
197
+ "content": "<extra_id_80>",
198
+ "lstrip": true,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32020": {
205
+ "content": "<extra_id_79>",
206
+ "lstrip": true,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32021": {
213
+ "content": "<extra_id_78>",
214
+ "lstrip": true,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32022": {
221
+ "content": "<extra_id_77>",
222
+ "lstrip": true,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32023": {
229
+ "content": "<extra_id_76>",
230
+ "lstrip": true,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32024": {
237
+ "content": "<extra_id_75>",
238
+ "lstrip": true,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32025": {
245
+ "content": "<extra_id_74>",
246
+ "lstrip": true,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32026": {
253
+ "content": "<extra_id_73>",
254
+ "lstrip": true,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32027": {
261
+ "content": "<extra_id_72>",
262
+ "lstrip": true,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32028": {
269
+ "content": "<extra_id_71>",
270
+ "lstrip": true,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32029": {
277
+ "content": "<extra_id_70>",
278
+ "lstrip": true,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32030": {
285
+ "content": "<extra_id_69>",
286
+ "lstrip": true,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32031": {
293
+ "content": "<extra_id_68>",
294
+ "lstrip": true,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32032": {
301
+ "content": "<extra_id_67>",
302
+ "lstrip": true,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32033": {
309
+ "content": "<extra_id_66>",
310
+ "lstrip": true,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32034": {
317
+ "content": "<extra_id_65>",
318
+ "lstrip": true,
319
+ "normalized": true,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32035": {
325
+ "content": "<extra_id_64>",
326
+ "lstrip": true,
327
+ "normalized": true,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32036": {
333
+ "content": "<extra_id_63>",
334
+ "lstrip": true,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32037": {
341
+ "content": "<extra_id_62>",
342
+ "lstrip": true,
343
+ "normalized": true,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32038": {
349
+ "content": "<extra_id_61>",
350
+ "lstrip": true,
351
+ "normalized": true,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32039": {
357
+ "content": "<extra_id_60>",
358
+ "lstrip": true,
359
+ "normalized": true,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32040": {
365
+ "content": "<extra_id_59>",
366
+ "lstrip": true,
367
+ "normalized": true,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32041": {
373
+ "content": "<extra_id_58>",
374
+ "lstrip": true,
375
+ "normalized": true,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32042": {
381
+ "content": "<extra_id_57>",
382
+ "lstrip": true,
383
+ "normalized": true,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32043": {
389
+ "content": "<extra_id_56>",
390
+ "lstrip": true,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32044": {
397
+ "content": "<extra_id_55>",
398
+ "lstrip": true,
399
+ "normalized": true,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32045": {
405
+ "content": "<extra_id_54>",
406
+ "lstrip": true,
407
+ "normalized": true,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32046": {
413
+ "content": "<extra_id_53>",
414
+ "lstrip": true,
415
+ "normalized": true,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32047": {
421
+ "content": "<extra_id_52>",
422
+ "lstrip": true,
423
+ "normalized": true,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32048": {
429
+ "content": "<extra_id_51>",
430
+ "lstrip": true,
431
+ "normalized": true,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32049": {
437
+ "content": "<extra_id_50>",
438
+ "lstrip": true,
439
+ "normalized": true,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32050": {
445
+ "content": "<extra_id_49>",
446
+ "lstrip": true,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32051": {
453
+ "content": "<extra_id_48>",
454
+ "lstrip": true,
455
+ "normalized": true,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32052": {
461
+ "content": "<extra_id_47>",
462
+ "lstrip": true,
463
+ "normalized": true,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32053": {
469
+ "content": "<extra_id_46>",
470
+ "lstrip": true,
471
+ "normalized": true,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32054": {
477
+ "content": "<extra_id_45>",
478
+ "lstrip": true,
479
+ "normalized": true,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32055": {
485
+ "content": "<extra_id_44>",
486
+ "lstrip": true,
487
+ "normalized": true,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32056": {
493
+ "content": "<extra_id_43>",
494
+ "lstrip": true,
495
+ "normalized": true,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32057": {
501
+ "content": "<extra_id_42>",
502
+ "lstrip": true,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32058": {
509
+ "content": "<extra_id_41>",
510
+ "lstrip": true,
511
+ "normalized": true,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32059": {
517
+ "content": "<extra_id_40>",
518
+ "lstrip": true,
519
+ "normalized": true,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32060": {
525
+ "content": "<extra_id_39>",
526
+ "lstrip": true,
527
+ "normalized": true,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32061": {
533
+ "content": "<extra_id_38>",
534
+ "lstrip": true,
535
+ "normalized": true,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32062": {
541
+ "content": "<extra_id_37>",
542
+ "lstrip": true,
543
+ "normalized": true,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32063": {
549
+ "content": "<extra_id_36>",
550
+ "lstrip": true,
551
+ "normalized": true,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32064": {
557
+ "content": "<extra_id_35>",
558
+ "lstrip": true,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32065": {
565
+ "content": "<extra_id_34>",
566
+ "lstrip": true,
567
+ "normalized": true,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32066": {
573
+ "content": "<extra_id_33>",
574
+ "lstrip": true,
575
+ "normalized": true,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32067": {
581
+ "content": "<extra_id_32>",
582
+ "lstrip": true,
583
+ "normalized": true,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32068": {
589
+ "content": "<extra_id_31>",
590
+ "lstrip": true,
591
+ "normalized": true,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32069": {
597
+ "content": "<extra_id_30>",
598
+ "lstrip": true,
599
+ "normalized": true,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32070": {
605
+ "content": "<extra_id_29>",
606
+ "lstrip": true,
607
+ "normalized": true,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32071": {
613
+ "content": "<extra_id_28>",
614
+ "lstrip": true,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32072": {
621
+ "content": "<extra_id_27>",
622
+ "lstrip": true,
623
+ "normalized": true,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32073": {
629
+ "content": "<extra_id_26>",
630
+ "lstrip": true,
631
+ "normalized": true,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32074": {
637
+ "content": "<extra_id_25>",
638
+ "lstrip": true,
639
+ "normalized": true,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32075": {
645
+ "content": "<extra_id_24>",
646
+ "lstrip": true,
647
+ "normalized": true,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32076": {
653
+ "content": "<extra_id_23>",
654
+ "lstrip": true,
655
+ "normalized": true,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32077": {
661
+ "content": "<extra_id_22>",
662
+ "lstrip": true,
663
+ "normalized": true,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32078": {
669
+ "content": "<extra_id_21>",
670
+ "lstrip": true,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32079": {
677
+ "content": "<extra_id_20>",
678
+ "lstrip": true,
679
+ "normalized": true,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32080": {
685
+ "content": "<extra_id_19>",
686
+ "lstrip": true,
687
+ "normalized": true,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32081": {
693
+ "content": "<extra_id_18>",
694
+ "lstrip": true,
695
+ "normalized": true,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32082": {
701
+ "content": "<extra_id_17>",
702
+ "lstrip": true,
703
+ "normalized": true,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32083": {
709
+ "content": "<extra_id_16>",
710
+ "lstrip": true,
711
+ "normalized": true,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32084": {
717
+ "content": "<extra_id_15>",
718
+ "lstrip": true,
719
+ "normalized": true,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32085": {
725
+ "content": "<extra_id_14>",
726
+ "lstrip": true,
727
+ "normalized": true,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32086": {
733
+ "content": "<extra_id_13>",
734
+ "lstrip": true,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32087": {
741
+ "content": "<extra_id_12>",
742
+ "lstrip": true,
743
+ "normalized": true,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32088": {
749
+ "content": "<extra_id_11>",
750
+ "lstrip": true,
751
+ "normalized": true,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32089": {
757
+ "content": "<extra_id_10>",
758
+ "lstrip": true,
759
+ "normalized": true,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32090": {
765
+ "content": "<extra_id_9>",
766
+ "lstrip": true,
767
+ "normalized": true,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32091": {
773
+ "content": "<extra_id_8>",
774
+ "lstrip": true,
775
+ "normalized": true,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32092": {
781
+ "content": "<extra_id_7>",
782
+ "lstrip": true,
783
+ "normalized": true,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32093": {
789
+ "content": "<extra_id_6>",
790
+ "lstrip": true,
791
+ "normalized": true,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32094": {
797
+ "content": "<extra_id_5>",
798
+ "lstrip": true,
799
+ "normalized": true,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32095": {
805
+ "content": "<extra_id_4>",
806
+ "lstrip": true,
807
+ "normalized": true,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32096": {
813
+ "content": "<extra_id_3>",
814
+ "lstrip": true,
815
+ "normalized": true,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32097": {
821
+ "content": "<extra_id_2>",
822
+ "lstrip": true,
823
+ "normalized": true,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "32098": {
829
+ "content": "<extra_id_1>",
830
+ "lstrip": true,
831
+ "normalized": true,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "32099": {
837
+ "content": "<extra_id_0>",
838
+ "lstrip": true,
839
+ "normalized": true,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ }
844
+ },
845
+ "additional_special_tokens": [
846
+ "<extra_id_99>",
847
+ "<extra_id_98>",
848
+ "<extra_id_97>",
849
+ "<extra_id_96>",
850
+ "<extra_id_95>",
851
+ "<extra_id_94>",
852
+ "<extra_id_93>",
853
+ "<extra_id_92>",
854
+ "<extra_id_91>",
855
+ "<extra_id_90>",
856
+ "<extra_id_89>",
857
+ "<extra_id_88>",
858
+ "<extra_id_87>",
859
+ "<extra_id_86>",
860
+ "<extra_id_85>",
861
+ "<extra_id_84>",
862
+ "<extra_id_83>",
863
+ "<extra_id_82>",
864
+ "<extra_id_81>",
865
+ "<extra_id_80>",
866
+ "<extra_id_79>",
867
+ "<extra_id_78>",
868
+ "<extra_id_77>",
869
+ "<extra_id_76>",
870
+ "<extra_id_75>",
871
+ "<extra_id_74>",
872
+ "<extra_id_73>",
873
+ "<extra_id_72>",
874
+ "<extra_id_71>",
875
+ "<extra_id_70>",
876
+ "<extra_id_69>",
877
+ "<extra_id_68>",
878
+ "<extra_id_67>",
879
+ "<extra_id_66>",
880
+ "<extra_id_65>",
881
+ "<extra_id_64>",
882
+ "<extra_id_63>",
883
+ "<extra_id_62>",
884
+ "<extra_id_61>",
885
+ "<extra_id_60>",
886
+ "<extra_id_59>",
887
+ "<extra_id_58>",
888
+ "<extra_id_57>",
889
+ "<extra_id_56>",
890
+ "<extra_id_55>",
891
+ "<extra_id_54>",
892
+ "<extra_id_53>",
893
+ "<extra_id_52>",
894
+ "<extra_id_51>",
895
+ "<extra_id_50>",
896
+ "<extra_id_49>",
897
+ "<extra_id_48>",
898
+ "<extra_id_47>",
899
+ "<extra_id_46>",
900
+ "<extra_id_45>",
901
+ "<extra_id_44>",
902
+ "<extra_id_43>",
903
+ "<extra_id_42>",
904
+ "<extra_id_41>",
905
+ "<extra_id_40>",
906
+ "<extra_id_39>",
907
+ "<extra_id_38>",
908
+ "<extra_id_37>",
909
+ "<extra_id_36>",
910
+ "<extra_id_35>",
911
+ "<extra_id_34>",
912
+ "<extra_id_33>",
913
+ "<extra_id_32>",
914
+ "<extra_id_31>",
915
+ "<extra_id_30>",
916
+ "<extra_id_29>",
917
+ "<extra_id_28>",
918
+ "<extra_id_27>",
919
+ "<extra_id_26>",
920
+ "<extra_id_25>",
921
+ "<extra_id_24>",
922
+ "<extra_id_23>",
923
+ "<extra_id_22>",
924
+ "<extra_id_21>",
925
+ "<extra_id_20>",
926
+ "<extra_id_19>",
927
+ "<extra_id_18>",
928
+ "<extra_id_17>",
929
+ "<extra_id_16>",
930
+ "<extra_id_15>",
931
+ "<extra_id_14>",
932
+ "<extra_id_13>",
933
+ "<extra_id_12>",
934
+ "<extra_id_11>",
935
+ "<extra_id_10>",
936
+ "<extra_id_9>",
937
+ "<extra_id_8>",
938
+ "<extra_id_7>",
939
+ "<extra_id_6>",
940
+ "<extra_id_5>",
941
+ "<extra_id_4>",
942
+ "<extra_id_3>",
943
+ "<extra_id_2>",
944
+ "<extra_id_1>",
945
+ "<extra_id_0>"
946
+ ],
947
+ "bos_token": "<s>",
948
+ "clean_up_tokenization_spaces": false,
949
+ "cls_token": "<s>",
950
+ "eos_token": "</s>",
951
+ "errors": "replace",
952
+ "mask_token": "<mask>",
953
+ "model_max_length": 512,
954
+ "pad_token": "<pad>",
955
+ "sep_token": "</s>",
956
+ "tokenizer_class": "RobertaTokenizer",
957
+ "trim_offsets": true,
958
+ "unk_token": "<unk>"
959
+ }
trainer_state.json ADDED
@@ -0,0 +1,1013 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 14090,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07097232079488999,
13
+ "grad_norm": 4.760485649108887,
14
+ "learning_rate": 1.2411284599006388e-05,
15
+ "loss": 5.3493,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.14194464158977999,
20
+ "grad_norm": 3.876619577407837,
21
+ "learning_rate": 1.2322569198012776e-05,
22
+ "loss": 4.314,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.21291696238466998,
27
+ "grad_norm": 3.3549132347106934,
28
+ "learning_rate": 1.2233853797019163e-05,
29
+ "loss": 3.8419,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.28388928317955997,
34
+ "grad_norm": 2.582584857940674,
35
+ "learning_rate": 1.214513839602555e-05,
36
+ "loss": 3.6877,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.35486160397445,
41
+ "grad_norm": 3.2531728744506836,
42
+ "learning_rate": 1.2056422995031938e-05,
43
+ "loss": 3.5523,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.42583392476933996,
48
+ "grad_norm": 26.283876419067383,
49
+ "learning_rate": 1.1967707594038326e-05,
50
+ "loss": 3.5161,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.49680624556423,
55
+ "grad_norm": 3.0806777477264404,
56
+ "learning_rate": 1.1878992193044713e-05,
57
+ "loss": 3.496,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.5677785663591199,
62
+ "grad_norm": 2.6790292263031006,
63
+ "learning_rate": 1.17902767920511e-05,
64
+ "loss": 3.4429,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.63875088715401,
69
+ "grad_norm": 2.5105574131011963,
70
+ "learning_rate": 1.1701561391057488e-05,
71
+ "loss": 3.4733,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.7097232079489,
76
+ "grad_norm": 2.3946118354797363,
77
+ "learning_rate": 1.1612845990063876e-05,
78
+ "loss": 3.4635,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.7806955287437899,
83
+ "grad_norm": 2.8345706462860107,
84
+ "learning_rate": 1.1524130589070263e-05,
85
+ "loss": 3.3713,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.8516678495386799,
90
+ "grad_norm": 2.603573799133301,
91
+ "learning_rate": 1.143541518807665e-05,
92
+ "loss": 3.345,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.9226401703335699,
97
+ "grad_norm": 2.7637786865234375,
98
+ "learning_rate": 1.1346699787083038e-05,
99
+ "loss": 3.4174,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.99361249112846,
104
+ "grad_norm": 3.634453296661377,
105
+ "learning_rate": 1.1257984386089426e-05,
106
+ "loss": 3.3344,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 1.0645848119233499,
111
+ "grad_norm": 3.2783639430999756,
112
+ "learning_rate": 1.1169268985095813e-05,
113
+ "loss": 3.2603,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 1.1355571327182399,
118
+ "grad_norm": 12.153242111206055,
119
+ "learning_rate": 1.1080553584102201e-05,
120
+ "loss": 3.2665,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 1.20652945351313,
125
+ "grad_norm": 3.7843754291534424,
126
+ "learning_rate": 1.0991838183108588e-05,
127
+ "loss": 3.2353,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 1.27750177430802,
132
+ "grad_norm": 3.065302848815918,
133
+ "learning_rate": 1.0903122782114976e-05,
134
+ "loss": 3.2399,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 1.34847409510291,
139
+ "grad_norm": 5.1582183837890625,
140
+ "learning_rate": 1.0814407381121363e-05,
141
+ "loss": 3.2087,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 1.4194464158978,
146
+ "grad_norm": 3.7378036975860596,
147
+ "learning_rate": 1.072569198012775e-05,
148
+ "loss": 3.1919,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 1.49041873669269,
153
+ "grad_norm": 3.0015852451324463,
154
+ "learning_rate": 1.0636976579134138e-05,
155
+ "loss": 3.2515,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 1.56139105748758,
160
+ "grad_norm": 2.782742977142334,
161
+ "learning_rate": 1.0548261178140526e-05,
162
+ "loss": 3.182,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 1.6323633782824698,
167
+ "grad_norm": 2.8899967670440674,
168
+ "learning_rate": 1.0459545777146914e-05,
169
+ "loss": 3.2035,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 1.7033356990773598,
174
+ "grad_norm": 3.529968500137329,
175
+ "learning_rate": 1.0370830376153301e-05,
176
+ "loss": 3.2547,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 1.7743080198722498,
181
+ "grad_norm": 3.1597557067871094,
182
+ "learning_rate": 1.0282114975159689e-05,
183
+ "loss": 3.2193,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 1.8452803406671399,
188
+ "grad_norm": 2.7804019451141357,
189
+ "learning_rate": 1.0193399574166074e-05,
190
+ "loss": 3.1883,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 1.9162526614620297,
195
+ "grad_norm": 3.4074594974517822,
196
+ "learning_rate": 1.0104684173172464e-05,
197
+ "loss": 3.1894,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 1.9872249822569197,
202
+ "grad_norm": 3.2770557403564453,
203
+ "learning_rate": 1.0015968772178851e-05,
204
+ "loss": 3.1904,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 2.0581973030518097,
209
+ "grad_norm": 3.2407679557800293,
210
+ "learning_rate": 9.927253371185239e-06,
211
+ "loss": 3.0811,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 2.1291696238466997,
216
+ "grad_norm": 2.982088565826416,
217
+ "learning_rate": 9.838537970191626e-06,
218
+ "loss": 3.0856,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 2.2001419446415897,
223
+ "grad_norm": 3.4891321659088135,
224
+ "learning_rate": 9.749822569198014e-06,
225
+ "loss": 3.0932,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 2.2711142654364798,
230
+ "grad_norm": 2.988189220428467,
231
+ "learning_rate": 9.6611071682044e-06,
232
+ "loss": 3.0661,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 2.34208658623137,
237
+ "grad_norm": 2.7912137508392334,
238
+ "learning_rate": 9.572391767210789e-06,
239
+ "loss": 3.0924,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 2.41305890702626,
244
+ "grad_norm": 3.0504982471466064,
245
+ "learning_rate": 9.483676366217176e-06,
246
+ "loss": 3.0704,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 2.48403122782115,
251
+ "grad_norm": 3.195739984512329,
252
+ "learning_rate": 9.394960965223564e-06,
253
+ "loss": 3.06,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 2.55500354861604,
258
+ "grad_norm": 6.643301010131836,
259
+ "learning_rate": 9.306245564229951e-06,
260
+ "loss": 3.0857,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 2.62597586941093,
265
+ "grad_norm": 2.8578591346740723,
266
+ "learning_rate": 9.217530163236339e-06,
267
+ "loss": 3.0512,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 2.69694819020582,
272
+ "grad_norm": 3.1686370372772217,
273
+ "learning_rate": 9.128814762242725e-06,
274
+ "loss": 3.1005,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 2.7679205110007095,
279
+ "grad_norm": 2.9187655448913574,
280
+ "learning_rate": 9.040099361249114e-06,
281
+ "loss": 3.0878,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 2.8388928317956,
286
+ "grad_norm": 3.5484399795532227,
287
+ "learning_rate": 8.951383960255501e-06,
288
+ "loss": 3.0252,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 2.9098651525904895,
293
+ "grad_norm": 3.374964714050293,
294
+ "learning_rate": 8.862668559261889e-06,
295
+ "loss": 3.0888,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 2.98083747338538,
300
+ "grad_norm": 3.1180434226989746,
301
+ "learning_rate": 8.773953158268276e-06,
302
+ "loss": 3.0332,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 3.0518097941802695,
307
+ "grad_norm": 3.4749999046325684,
308
+ "learning_rate": 8.685237757274662e-06,
309
+ "loss": 3.031,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 3.1227821149751596,
314
+ "grad_norm": 3.021486282348633,
315
+ "learning_rate": 8.59652235628105e-06,
316
+ "loss": 3.0399,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 3.1937544357700496,
321
+ "grad_norm": 3.392218589782715,
322
+ "learning_rate": 8.507806955287439e-06,
323
+ "loss": 2.9733,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 3.2647267565649396,
328
+ "grad_norm": 2.912814140319824,
329
+ "learning_rate": 8.419091554293826e-06,
330
+ "loss": 2.9437,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 3.3356990773598296,
335
+ "grad_norm": 4.143916606903076,
336
+ "learning_rate": 8.330376153300214e-06,
337
+ "loss": 2.9484,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 3.4066713981547196,
342
+ "grad_norm": 12.112326622009277,
343
+ "learning_rate": 8.241660752306602e-06,
344
+ "loss": 2.9534,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 3.4776437189496097,
349
+ "grad_norm": 3.6819448471069336,
350
+ "learning_rate": 8.152945351312987e-06,
351
+ "loss": 2.9621,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 3.5486160397444997,
356
+ "grad_norm": 3.4722225666046143,
357
+ "learning_rate": 8.064229950319375e-06,
358
+ "loss": 2.9712,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 3.6195883605393897,
363
+ "grad_norm": 3.237942934036255,
364
+ "learning_rate": 7.975514549325764e-06,
365
+ "loss": 3.0101,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 3.6905606813342797,
370
+ "grad_norm": 2.8785219192504883,
371
+ "learning_rate": 7.886799148332152e-06,
372
+ "loss": 2.9564,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 3.7615330021291697,
377
+ "grad_norm": 3.193901777267456,
378
+ "learning_rate": 7.798083747338539e-06,
379
+ "loss": 2.9435,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 3.8325053229240598,
384
+ "grad_norm": 2.641021490097046,
385
+ "learning_rate": 7.709368346344927e-06,
386
+ "loss": 2.9404,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 3.90347764371895,
391
+ "grad_norm": 2.879225492477417,
392
+ "learning_rate": 7.6206529453513125e-06,
393
+ "loss": 2.9642,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 3.9744499645138394,
398
+ "grad_norm": 2.779848575592041,
399
+ "learning_rate": 7.531937544357701e-06,
400
+ "loss": 2.991,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 4.04542228530873,
405
+ "grad_norm": 4.226039886474609,
406
+ "learning_rate": 7.443222143364088e-06,
407
+ "loss": 2.8704,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 4.116394606103619,
412
+ "grad_norm": 3.5658841133117676,
413
+ "learning_rate": 7.354506742370476e-06,
414
+ "loss": 2.8641,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 4.18736692689851,
419
+ "grad_norm": 2.6197798252105713,
420
+ "learning_rate": 7.265791341376864e-06,
421
+ "loss": 2.8462,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 4.258339247693399,
426
+ "grad_norm": 2.7553303241729736,
427
+ "learning_rate": 7.17707594038325e-06,
428
+ "loss": 2.882,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 4.32931156848829,
433
+ "grad_norm": 2.9696245193481445,
434
+ "learning_rate": 7.0883605393896376e-06,
435
+ "loss": 2.9033,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 4.4002838892831795,
440
+ "grad_norm": 3.14622163772583,
441
+ "learning_rate": 6.999645138396026e-06,
442
+ "loss": 2.9003,
443
+ "step": 6200
444
+ },
445
+ {
446
+ "epoch": 4.47125621007807,
447
+ "grad_norm": 3.744727849960327,
448
+ "learning_rate": 6.9109297374024135e-06,
449
+ "loss": 2.8839,
450
+ "step": 6300
451
+ },
452
+ {
453
+ "epoch": 4.5422285308729595,
454
+ "grad_norm": 3.2394585609436035,
455
+ "learning_rate": 6.822214336408801e-06,
456
+ "loss": 2.9144,
457
+ "step": 6400
458
+ },
459
+ {
460
+ "epoch": 4.61320085166785,
461
+ "grad_norm": 3.425605535507202,
462
+ "learning_rate": 6.733498935415189e-06,
463
+ "loss": 2.9345,
464
+ "step": 6500
465
+ },
466
+ {
467
+ "epoch": 4.68417317246274,
468
+ "grad_norm": 2.960824489593506,
469
+ "learning_rate": 6.644783534421575e-06,
470
+ "loss": 2.8784,
471
+ "step": 6600
472
+ },
473
+ {
474
+ "epoch": 4.755145493257629,
475
+ "grad_norm": 2.8103156089782715,
476
+ "learning_rate": 6.556068133427963e-06,
477
+ "loss": 2.9073,
478
+ "step": 6700
479
+ },
480
+ {
481
+ "epoch": 4.82611781405252,
482
+ "grad_norm": 3.3681435585021973,
483
+ "learning_rate": 6.467352732434351e-06,
484
+ "loss": 2.8941,
485
+ "step": 6800
486
+ },
487
+ {
488
+ "epoch": 4.897090134847409,
489
+ "grad_norm": 2.99110746383667,
490
+ "learning_rate": 6.3786373314407386e-06,
491
+ "loss": 2.8776,
492
+ "step": 6900
493
+ },
494
+ {
495
+ "epoch": 4.9680624556423,
496
+ "grad_norm": 3.0673208236694336,
497
+ "learning_rate": 6.289921930447126e-06,
498
+ "loss": 2.8941,
499
+ "step": 7000
500
+ },
501
+ {
502
+ "epoch": 5.039034776437189,
503
+ "grad_norm": 3.0405173301696777,
504
+ "learning_rate": 6.201206529453514e-06,
505
+ "loss": 2.8133,
506
+ "step": 7100
507
+ },
508
+ {
509
+ "epoch": 5.11000709723208,
510
+ "grad_norm": 2.673586368560791,
511
+ "learning_rate": 6.112491128459901e-06,
512
+ "loss": 2.8009,
513
+ "step": 7200
514
+ },
515
+ {
516
+ "epoch": 5.180979418026969,
517
+ "grad_norm": 2.86667799949646,
518
+ "learning_rate": 6.023775727466288e-06,
519
+ "loss": 2.8341,
520
+ "step": 7300
521
+ },
522
+ {
523
+ "epoch": 5.25195173882186,
524
+ "grad_norm": 2.725980758666992,
525
+ "learning_rate": 5.935060326472676e-06,
526
+ "loss": 2.8206,
527
+ "step": 7400
528
+ },
529
+ {
530
+ "epoch": 5.322924059616749,
531
+ "grad_norm": 9.25928783416748,
532
+ "learning_rate": 5.846344925479064e-06,
533
+ "loss": 2.8782,
534
+ "step": 7500
535
+ },
536
+ {
537
+ "epoch": 5.39389638041164,
538
+ "grad_norm": 3.619668960571289,
539
+ "learning_rate": 5.75762952448545e-06,
540
+ "loss": 2.8083,
541
+ "step": 7600
542
+ },
543
+ {
544
+ "epoch": 5.464868701206529,
545
+ "grad_norm": 4.820442199707031,
546
+ "learning_rate": 5.668914123491839e-06,
547
+ "loss": 2.8051,
548
+ "step": 7700
549
+ },
550
+ {
551
+ "epoch": 5.53584102200142,
552
+ "grad_norm": 3.3483476638793945,
553
+ "learning_rate": 5.580198722498226e-06,
554
+ "loss": 2.7862,
555
+ "step": 7800
556
+ },
557
+ {
558
+ "epoch": 5.606813342796309,
559
+ "grad_norm": 3.04085373878479,
560
+ "learning_rate": 5.491483321504613e-06,
561
+ "loss": 2.786,
562
+ "step": 7900
563
+ },
564
+ {
565
+ "epoch": 5.6777856635912,
566
+ "grad_norm": 6.183100700378418,
567
+ "learning_rate": 5.402767920511001e-06,
568
+ "loss": 2.8541,
569
+ "step": 8000
570
+ },
571
+ {
572
+ "epoch": 5.748757984386089,
573
+ "grad_norm": 3.20927357673645,
574
+ "learning_rate": 5.314052519517389e-06,
575
+ "loss": 2.8428,
576
+ "step": 8100
577
+ },
578
+ {
579
+ "epoch": 5.819730305180979,
580
+ "grad_norm": 2.7963485717773438,
581
+ "learning_rate": 5.2253371185237755e-06,
582
+ "loss": 2.8391,
583
+ "step": 8200
584
+ },
585
+ {
586
+ "epoch": 5.8907026259758695,
587
+ "grad_norm": 2.9603395462036133,
588
+ "learning_rate": 5.136621717530164e-06,
589
+ "loss": 2.8483,
590
+ "step": 8300
591
+ },
592
+ {
593
+ "epoch": 5.961674946770759,
594
+ "grad_norm": 3.2761342525482178,
595
+ "learning_rate": 5.047906316536551e-06,
596
+ "loss": 2.8908,
597
+ "step": 8400
598
+ },
599
+ {
600
+ "epoch": 6.0326472675656495,
601
+ "grad_norm": 2.543006181716919,
602
+ "learning_rate": 4.959190915542938e-06,
603
+ "loss": 2.7455,
604
+ "step": 8500
605
+ },
606
+ {
607
+ "epoch": 6.103619588360539,
608
+ "grad_norm": 2.7663486003875732,
609
+ "learning_rate": 4.870475514549326e-06,
610
+ "loss": 2.781,
611
+ "step": 8600
612
+ },
613
+ {
614
+ "epoch": 6.1745919091554295,
615
+ "grad_norm": 3.1819772720336914,
616
+ "learning_rate": 4.781760113555713e-06,
617
+ "loss": 2.8151,
618
+ "step": 8700
619
+ },
620
+ {
621
+ "epoch": 6.245564229950319,
622
+ "grad_norm": 3.4800798892974854,
623
+ "learning_rate": 4.693044712562101e-06,
624
+ "loss": 2.742,
625
+ "step": 8800
626
+ },
627
+ {
628
+ "epoch": 6.31653655074521,
629
+ "grad_norm": 2.997176170349121,
630
+ "learning_rate": 4.604329311568489e-06,
631
+ "loss": 2.7626,
632
+ "step": 8900
633
+ },
634
+ {
635
+ "epoch": 6.387508871540099,
636
+ "grad_norm": 2.6546881198883057,
637
+ "learning_rate": 4.515613910574876e-06,
638
+ "loss": 2.7803,
639
+ "step": 9000
640
+ },
641
+ {
642
+ "epoch": 6.45848119233499,
643
+ "grad_norm": 3.736813545227051,
644
+ "learning_rate": 4.426898509581263e-06,
645
+ "loss": 2.7491,
646
+ "step": 9100
647
+ },
648
+ {
649
+ "epoch": 6.529453513129879,
650
+ "grad_norm": 2.904879331588745,
651
+ "learning_rate": 4.3381831085876515e-06,
652
+ "loss": 2.7707,
653
+ "step": 9200
654
+ },
655
+ {
656
+ "epoch": 6.60042583392477,
657
+ "grad_norm": 3.1349782943725586,
658
+ "learning_rate": 4.249467707594038e-06,
659
+ "loss": 2.7715,
660
+ "step": 9300
661
+ },
662
+ {
663
+ "epoch": 6.671398154719659,
664
+ "grad_norm": 3.8655664920806885,
665
+ "learning_rate": 4.160752306600426e-06,
666
+ "loss": 2.8137,
667
+ "step": 9400
668
+ },
669
+ {
670
+ "epoch": 6.74237047551455,
671
+ "grad_norm": 3.0926291942596436,
672
+ "learning_rate": 4.072036905606814e-06,
673
+ "loss": 2.7606,
674
+ "step": 9500
675
+ },
676
+ {
677
+ "epoch": 6.813342796309439,
678
+ "grad_norm": 2.9830901622772217,
679
+ "learning_rate": 3.983321504613201e-06,
680
+ "loss": 2.7696,
681
+ "step": 9600
682
+ },
683
+ {
684
+ "epoch": 6.884315117104329,
685
+ "grad_norm": 2.9719297885894775,
686
+ "learning_rate": 3.894606103619588e-06,
687
+ "loss": 2.7477,
688
+ "step": 9700
689
+ },
690
+ {
691
+ "epoch": 6.955287437899219,
692
+ "grad_norm": 4.136593818664551,
693
+ "learning_rate": 3.805890702625976e-06,
694
+ "loss": 2.7814,
695
+ "step": 9800
696
+ },
697
+ {
698
+ "epoch": 7.026259758694109,
699
+ "grad_norm": 3.006192922592163,
700
+ "learning_rate": 3.7171753016323633e-06,
701
+ "loss": 2.7316,
702
+ "step": 9900
703
+ },
704
+ {
705
+ "epoch": 7.097232079488999,
706
+ "grad_norm": 3.204758644104004,
707
+ "learning_rate": 3.6284599006387512e-06,
708
+ "loss": 2.7784,
709
+ "step": 10000
710
+ },
711
+ {
712
+ "epoch": 7.168204400283889,
713
+ "grad_norm": 4.11678409576416,
714
+ "learning_rate": 3.5397444996451388e-06,
715
+ "loss": 2.7377,
716
+ "step": 10100
717
+ },
718
+ {
719
+ "epoch": 7.239176721078779,
720
+ "grad_norm": 3.0145442485809326,
721
+ "learning_rate": 3.451029098651526e-06,
722
+ "loss": 2.7327,
723
+ "step": 10200
724
+ },
725
+ {
726
+ "epoch": 7.310149041873669,
727
+ "grad_norm": 2.759552240371704,
728
+ "learning_rate": 3.362313697657914e-06,
729
+ "loss": 2.6663,
730
+ "step": 10300
731
+ },
732
+ {
733
+ "epoch": 7.3811213626685594,
734
+ "grad_norm": 3.0694785118103027,
735
+ "learning_rate": 3.2735982966643013e-06,
736
+ "loss": 2.7523,
737
+ "step": 10400
738
+ },
739
+ {
740
+ "epoch": 7.452093683463449,
741
+ "grad_norm": 2.6538655757904053,
742
+ "learning_rate": 3.1848828956706884e-06,
743
+ "loss": 2.749,
744
+ "step": 10500
745
+ },
746
+ {
747
+ "epoch": 7.5230660042583395,
748
+ "grad_norm": 3.4055073261260986,
749
+ "learning_rate": 3.0961674946770763e-06,
750
+ "loss": 2.7119,
751
+ "step": 10600
752
+ },
753
+ {
754
+ "epoch": 7.594038325053229,
755
+ "grad_norm": 2.686981439590454,
756
+ "learning_rate": 3.0074520936834634e-06,
757
+ "loss": 2.6696,
758
+ "step": 10700
759
+ },
760
+ {
761
+ "epoch": 7.6650106458481195,
762
+ "grad_norm": 3.1230781078338623,
763
+ "learning_rate": 2.918736692689851e-06,
764
+ "loss": 2.7344,
765
+ "step": 10800
766
+ },
767
+ {
768
+ "epoch": 7.735982966643009,
769
+ "grad_norm": 2.9182968139648438,
770
+ "learning_rate": 2.830021291696239e-06,
771
+ "loss": 2.7724,
772
+ "step": 10900
773
+ },
774
+ {
775
+ "epoch": 7.8069552874379,
776
+ "grad_norm": 4.071280002593994,
777
+ "learning_rate": 2.741305890702626e-06,
778
+ "loss": 2.7562,
779
+ "step": 11000
780
+ },
781
+ {
782
+ "epoch": 7.877927608232789,
783
+ "grad_norm": 2.9077835083007812,
784
+ "learning_rate": 2.6525904897090135e-06,
785
+ "loss": 2.7375,
786
+ "step": 11100
787
+ },
788
+ {
789
+ "epoch": 7.948899929027679,
790
+ "grad_norm": 3.786334276199341,
791
+ "learning_rate": 2.563875088715401e-06,
792
+ "loss": 2.7451,
793
+ "step": 11200
794
+ },
795
+ {
796
+ "epoch": 8.01987224982257,
797
+ "grad_norm": 3.843573808670044,
798
+ "learning_rate": 2.4751596877217886e-06,
799
+ "loss": 2.7024,
800
+ "step": 11300
801
+ },
802
+ {
803
+ "epoch": 8.09084457061746,
804
+ "grad_norm": 3.3538873195648193,
805
+ "learning_rate": 2.386444286728176e-06,
806
+ "loss": 2.7569,
807
+ "step": 11400
808
+ },
809
+ {
810
+ "epoch": 8.161816891412348,
811
+ "grad_norm": 3.028632879257202,
812
+ "learning_rate": 2.2977288857345636e-06,
813
+ "loss": 2.7473,
814
+ "step": 11500
815
+ },
816
+ {
817
+ "epoch": 8.232789212207239,
818
+ "grad_norm": 3.1207797527313232,
819
+ "learning_rate": 2.209013484740951e-06,
820
+ "loss": 2.7304,
821
+ "step": 11600
822
+ },
823
+ {
824
+ "epoch": 8.30376153300213,
825
+ "grad_norm": 2.9007532596588135,
826
+ "learning_rate": 2.1202980837473386e-06,
827
+ "loss": 2.6945,
828
+ "step": 11700
829
+ },
830
+ {
831
+ "epoch": 8.37473385379702,
832
+ "grad_norm": 3.2682387828826904,
833
+ "learning_rate": 2.031582682753726e-06,
834
+ "loss": 2.6944,
835
+ "step": 11800
836
+ },
837
+ {
838
+ "epoch": 8.445706174591908,
839
+ "grad_norm": 2.944650173187256,
840
+ "learning_rate": 1.9428672817601137e-06,
841
+ "loss": 2.6788,
842
+ "step": 11900
843
+ },
844
+ {
845
+ "epoch": 8.516678495386799,
846
+ "grad_norm": 3.6891725063323975,
847
+ "learning_rate": 1.8541518807665012e-06,
848
+ "loss": 2.6576,
849
+ "step": 12000
850
+ },
851
+ {
852
+ "epoch": 8.58765081618169,
853
+ "grad_norm": 3.5069870948791504,
854
+ "learning_rate": 1.7654364797728887e-06,
855
+ "loss": 2.6916,
856
+ "step": 12100
857
+ },
858
+ {
859
+ "epoch": 8.65862313697658,
860
+ "grad_norm": 3.2562413215637207,
861
+ "learning_rate": 1.676721078779276e-06,
862
+ "loss": 2.709,
863
+ "step": 12200
864
+ },
865
+ {
866
+ "epoch": 8.729595457771469,
867
+ "grad_norm": 2.882202386856079,
868
+ "learning_rate": 1.5880056777856637e-06,
869
+ "loss": 2.6932,
870
+ "step": 12300
871
+ },
872
+ {
873
+ "epoch": 8.800567778566359,
874
+ "grad_norm": 3.014678955078125,
875
+ "learning_rate": 1.499290276792051e-06,
876
+ "loss": 2.7494,
877
+ "step": 12400
878
+ },
879
+ {
880
+ "epoch": 8.87154009936125,
881
+ "grad_norm": 3.5019314289093018,
882
+ "learning_rate": 1.4105748757984388e-06,
883
+ "loss": 2.716,
884
+ "step": 12500
885
+ },
886
+ {
887
+ "epoch": 8.94251242015614,
888
+ "grad_norm": 3.2683048248291016,
889
+ "learning_rate": 1.321859474804826e-06,
890
+ "loss": 2.7186,
891
+ "step": 12600
892
+ },
893
+ {
894
+ "epoch": 9.013484740951029,
895
+ "grad_norm": 2.985898017883301,
896
+ "learning_rate": 1.2331440738112136e-06,
897
+ "loss": 2.7296,
898
+ "step": 12700
899
+ },
900
+ {
901
+ "epoch": 9.084457061745919,
902
+ "grad_norm": 3.0097787380218506,
903
+ "learning_rate": 1.1444286728176011e-06,
904
+ "loss": 2.7134,
905
+ "step": 12800
906
+ },
907
+ {
908
+ "epoch": 9.15542938254081,
909
+ "grad_norm": 3.375105142593384,
910
+ "learning_rate": 1.0557132718239887e-06,
911
+ "loss": 2.6976,
912
+ "step": 12900
913
+ },
914
+ {
915
+ "epoch": 9.2264017033357,
916
+ "grad_norm": 18.599666595458984,
917
+ "learning_rate": 9.669978708303762e-07,
918
+ "loss": 2.6748,
919
+ "step": 13000
920
+ },
921
+ {
922
+ "epoch": 9.297374024130589,
923
+ "grad_norm": 3.4463281631469727,
924
+ "learning_rate": 8.782824698367637e-07,
925
+ "loss": 2.6669,
926
+ "step": 13100
927
+ },
928
+ {
929
+ "epoch": 9.36834634492548,
930
+ "grad_norm": 3.3725767135620117,
931
+ "learning_rate": 7.895670688431512e-07,
932
+ "loss": 2.6394,
933
+ "step": 13200
934
+ },
935
+ {
936
+ "epoch": 9.43931866572037,
937
+ "grad_norm": 3.3101234436035156,
938
+ "learning_rate": 7.008516678495387e-07,
939
+ "loss": 2.7324,
940
+ "step": 13300
941
+ },
942
+ {
943
+ "epoch": 9.510290986515258,
944
+ "grad_norm": 3.0802764892578125,
945
+ "learning_rate": 6.121362668559262e-07,
946
+ "loss": 2.6929,
947
+ "step": 13400
948
+ },
949
+ {
950
+ "epoch": 9.581263307310149,
951
+ "grad_norm": 2.806544303894043,
952
+ "learning_rate": 5.234208658623137e-07,
953
+ "loss": 2.6382,
954
+ "step": 13500
955
+ },
956
+ {
957
+ "epoch": 9.65223562810504,
958
+ "grad_norm": 3.4582176208496094,
959
+ "learning_rate": 4.347054648687013e-07,
960
+ "loss": 2.694,
961
+ "step": 13600
962
+ },
963
+ {
964
+ "epoch": 9.72320794889993,
965
+ "grad_norm": 4.037984848022461,
966
+ "learning_rate": 3.459900638750887e-07,
967
+ "loss": 2.6497,
968
+ "step": 13700
969
+ },
970
+ {
971
+ "epoch": 9.794180269694818,
972
+ "grad_norm": 3.1365439891815186,
973
+ "learning_rate": 2.572746628814762e-07,
974
+ "loss": 2.705,
975
+ "step": 13800
976
+ },
977
+ {
978
+ "epoch": 9.865152590489709,
979
+ "grad_norm": 3.4496893882751465,
980
+ "learning_rate": 1.6855926188786376e-07,
981
+ "loss": 2.7123,
982
+ "step": 13900
983
+ },
984
+ {
985
+ "epoch": 9.9361249112846,
986
+ "grad_norm": 3.1736724376678467,
987
+ "learning_rate": 7.984386089425125e-08,
988
+ "loss": 2.7009,
989
+ "step": 14000
990
+ }
991
+ ],
992
+ "logging_steps": 100,
993
+ "max_steps": 14090,
994
+ "num_input_tokens_seen": 0,
995
+ "num_train_epochs": 10,
996
+ "save_steps": 500,
997
+ "stateful_callbacks": {
998
+ "TrainerControl": {
999
+ "args": {
1000
+ "should_epoch_stop": false,
1001
+ "should_evaluate": false,
1002
+ "should_log": false,
1003
+ "should_save": true,
1004
+ "should_training_stop": true
1005
+ },
1006
+ "attributes": {}
1007
+ }
1008
+ },
1009
+ "total_flos": 3.430320762257408e+16,
1010
+ "train_batch_size": 8,
1011
+ "trial_name": null,
1012
+ "trial_params": null
1013
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c45ab43fe46264d6e11791f5fdc05ea6e10f305aefba2211c1cd83eab1b502f8
3
+ size 5649
vocab.json ADDED
The diff for this file is too large to render. See raw diff